Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3075 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.1607. Min Act: -0.0001

Data Index: 782442 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.2081. Min Act: -0.0000

Data Index: 536850 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.2088. Min Act: -0.0000

Data Index: 59068 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.1591. Min Act: -0.0000

Data Index: 387154 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.1639. Min Act: -0.0000

Data Index: 767431 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.1318. Min Act: -0.0001

Data Index: 1230813 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.0995. Min Act: -0.0001

Data Index: 116084 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.0981. Min Act: -0.0001

Data Index: 581582 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.0924. Min Act: -0.0001

Data Index: 998185 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.0969. Min Act: -0.0001

Data Index: 1327851 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.0650. Min Act: -0.0001

Data Index: 1239526 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9987. Min Act: -0.0001

Data Index: 944582 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.0209. Min Act: -0.0000

Data Index: 1315505 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.0682. Min Act: -0.0001

Data Index: 934178 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.0064. Min Act: -0.0001

Data Index: 169380 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9971. Min Act: -0.0000

Data Index: 74128 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9576. Min Act: -0.0001

Data Index: 424204 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.0476. Min Act: -0.0001

Data Index: 628142 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.0987. Min Act: -0.0001

Data Index: 693366 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.0435. Min Act: -0.0001

Data Index: 407247 (C4 (Web Text))

Max Activating Token Index: 586